Senior System Software Engineer - AI

As a Senior Systems Software Engineer at WinAI, you will play a crucial role in solving client-side AI challenges on Windows PCs with limited resources. You will be partnering with NVIDIA software, research, architecture, and product teams to align strategies and technical needs for encouraging the ecosystem of AI on Windows RTX PCs. Collaboration with Microsoft will be essential to advance AI across critical domains such as graphics, web browsers, and edge devices by driving innovation in technologies like WindowsML, ONNX Runtime, and NVIDIA's proprietary libraries and driver stack. Your responsibilities will include improving performance on current and next-generation GPU architectures through in-depth analysis and optimization of AI models, data processing pipelines, and inference runtime features. You will also be identifying, evaluating, and implementing compute and memory optimization techniques for large AI models, such as quantization, distillation, and pruning, to fine-tune and compress models to fit edge devices. To qualify for this role, you should hold a Bachelor's, Master's, or PhD in Computer Science, Software Engineering, Mathematics, or a related field, or possess equivalent experience. Proficiency in C++ programming and debugging, along with a strong understanding of data structures and algorithms, is required. You should have at least 5 years of experience in AI inferencing pipelines and applications using ML/DL frameworks like ONNX RT, DirectML, PyTorch, and Tensor RT. Strong analytical and problem-solving abilities are essential, along with effective multitasking skills in a dynamic environment. Excellent written and oral communication skills are also necessary for successful collaboration with management and engineering teams. To stand out from the crowd, having an understanding of modern techniques in Machine Learning, Deep Neural Networks, and Generative AI, with relevant contributions to major open-source projects, will be advantageous. A consistent track record of delivering end-to-end products with geographically distributed teams in multinational product companies will also be a plus. Proficiency in lower-level system/GPU programming, CUDA, and developing high-performance systems, as well as hands-on experience with building applications using APIs like ONNX RT, DirectML, DirectX, PyTorch, TensorRT, and Vulkan, are highly desirable. At WinAI, we are committed to innovation and growth, offering competitive salaries and a generous benefits package. As an equal-opportunity employer, we value diversity within our company. If you are a creative and autonomous engineer with a genuine passion for technology, we welcome you to join our exclusive engineering teams that are experiencing unprecedented growth.,